germain-hug/NeurHal
Visual Correspondence Hallucination: Towards Geometric Reasoning (Under Review)
This project helps computer vision researchers and robotics engineers overcome limitations in traditional image matching. It takes two partially overlapping images and a specific point in the first image, then predicts where that point would be in the second image, even if it's hidden or out of view. This tool is designed for specialists working with image analysis, particularly in scenarios where complete visibility isn't guaranteed.
No commits in the last 6 months.
Use this if you need to precisely locate corresponding points between images, even when they are obscured or outside the visible frame, for tasks like camera pose estimation.
Not ideal if you only need to match clearly visible points between images, as simpler local feature matching methods might suffice.
Stars
29
Forks
—
Language
—
License
—
Last pushed
Jan 28, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/germain-hug/NeurHal"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jessevig/bertviz
BertViz: Visualize Attention in Transformer Models
inseq-team/inseq
Interpretability for sequence generation models 🐛 🔍
EleutherAI/knowledge-neurons
A library for finding knowledge neurons in pretrained transformer models.
hila-chefer/Transformer-MM-Explainability
[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for...
cdpierse/transformers-interpret
Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model...